replicate-study

Extract study design and generate analysis code for database replication.

243|60|Updated Apr 6, 2026
One-click install
npx skills add https://github.com/Aperivue/medsci-skills --skill replicate-study
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: replicate-study
Source: https://github.com/Aperivue/medsci-skills/tree/main/skills/replicate-study
Command: npx skills add https://github.com/Aperivue/medsci-skills --skill replicate-study

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Replicate-study enables researchers to transplant a published study methodology to a different database by extracting study design, mapping variables via a harmonization table, generating analysis code, and creating a replication difference report.

Core Features & Use Cases

  • Source paper analysis: extract study design, database details, exposure, outcomes, and covariates from a source paper.
  • Variable mapping & code generation: map variables to the target database and generate reproducible analysis scripts (Python + R) and a difference report.
  • Phase-driven workflow: Phase 1: Source Paper Analysis; Phase 2: Variable Mapping; Phase 3: Code Generation; Phase 4: Difference Report; Phase 5: Validation.
  • Output artifacts: structured replication_report.md, variable_mapping.csv, analysis_code.py/R, and results/ directory.

Quick Start

Provide the source paper, target database path, and optional harmonization table, then invoke the replication workflow to generate outputs.

Frequently Asked Questions about replicate-study

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I replicate a published study methodology using a different database?

To replicate a published study, you provide the source paper, a target database path, and an optional harmonization file. The workflow extracts the study design, maps variables, generates analysis code, and creates a replication difference report.

What is variable harmonization when mapping cohort data for a study replication?

Variable harmonization is the process of mapping variables from a source paper to a target database via a harmonization table. It ensures that exposure, outcomes, and covariates align correctly for accurate cohort analysis in the new database.

Can I generate both Python and R analysis scripts for a replicated cohort study?

Yes, study replication generates reproducible analysis scripts in both Python and R. The workflow produces analysis_code.py and analysis_code.R to execute the transplanted methodology on your target database.

What file formats do I need to provide as input for source paper analysis?

Source paper analysis accepts PDF, DOI, or markdown file formats as input. You provide the source paper along with a target database path to initiate the extraction of study design and variable mapping.

What outputs are generated after completing the study replication workflow?

The study replication workflow generates a structured replication_report.md, variable_mapping.csv, analysis_code.py/R scripts, and a results directory containing the complete replication artifacts for your target database.

Do I need a harmonization table to map variables for a study replication?

A harmonization table is an optional input for variable mapping during study replication. Providing it helps guide the accurate mapping of exposure, outcomes, and covariates from the source paper to the target database.